Lingfeng Shen

My name is Lingfeng Shen(沈凌峰), a second-year master student at Department of Computer Science, Johns Hopkins University, advised by Prof. Daniel Khashabi, and Prof. Philipp Koehn. Before that, I received my B.S. degree (Mathematics) from China Agricultural University. I'm actively looking for PhD and industry opportunities in 2024 Fall, don't hesitate to email me if there is a potential fit.

My current research interests include:

  • Understanding the emergent behaviors of foundation models (e.g., In-context learning): [1], [7]
  • Data-centric design in building foundation models: [2]
  • Security and robustness of foundation models: [2], [8]

    • I used to be interested in adversarial robustness [3], [4], backdoor robustness [5], and evaluation [5], [6]

    Email: lshen30[at]jhu.edu

    Github   /   Google Scholar   /   Semantic Scholar   /   Twitter   /   LinkedIn     

    		profile photo

    I use a so-called "geometric owl" as my avatar in most places.

    Selected Publications (* equal contribution, full publications can be found in my Google Scholar)

    The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
    Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
    Preprint 2024  
    paper  /  code  

    Do pretrained Transformers Really Learn In-context by Gradient Descent?
    Lingfeng Shen*, Aayush Mishra*, Daniel Khashabi
    Preprint 2023  
    paper  /  code  

    The Trickle-down Impact of Reward (In-)consistency on RLHF
    Lingfeng Shen,  Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu
    ICLR2024  
    paper  /  code  

    TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification
    Lingfeng Shen, Ze Zhang, Haiyun Jiang, Ying Chen
    ICLR2023  
    paper  

    On the Evaluation Metrics for Paraphrase Generation
    Lingfeng Shen, Lemao Liu, Haiyun Jiang, Shuming Shi
    EMNLP2022  
    paper  /  code

    Miscellaneous

  • Motorsports ignite my passion, particularly Formula 1. I'm ardently devoted to the Mercedes-AMG Petronas F1 Team.

  • The NBA also has a special place in my heart; I used to be a fan of Houston Rocket.

  • Off the screen, you'll often find me karting with friends or clocking laps on the race track or playing video games.

    		• profile photo

    Services

  • Reviewers: ICLR2024, NeurIPS 2023, ICML 2023, ACL 2023, AAAI 2023/2024, AAAI2022, EMNLP 2022/2023, ARR 2022/2023.





    • Updated at July 2023
    Thanks Jon Barron for this amazing work